Xander S.

Hey Truong H., can you help me understand your high-level goal? It sounds like you are trying to use a prompt saved inside the Phoenix server to run an LLM evaluator via the evals SDK. Does that sound right?

Darshan T. The bot looks correct here

Hey Andrei L., that error screen you show may be due to any number of issues. Can you describe what URL you are attempting to access or what action you are taking in the UI when you see it?

You are interested in the cost of entire traces as opposed to individual spans?

https://arize.com/docs/phoenix/tracing/how-to-tracing/setup-tracing/setup-sessions

Depending on your use case, you may also want to look into sessions.

atexit feels like the right way to handle this. Documentation on how to handle this could be helpful, though.

Hey Ayub K., we don't have affordances for that in the UI. You should be able to accomplish this using the client by pulling and combing the various datasets. https://arize-phoenix.readthedocs.io/projects/client/en/latest/api/datasets.html

I take it the session IDs that are colliding are coming from different teams who don't know what session IDs the other teams are using?

I see, thanks for the context. The easiest unblock for now then is to ensure that the session ID is globally unique. How are those session IDs being generated now?